Skip to content
SSCodeAI
日本語English

takumi

A model-agnostic orchestration platform for verifiable agentic software delivery.

Updated View as Markdown

takumi

takumi is an open-source orchestration layer for AI software delivery. It is not a single coding agent, a Pi wrapper, or a DeepSeek fork. Takumi coordinates pluggable agent runtimes through explicit workflows, quality gates, artifacts, traceability, and independent verification.

Agents propose. Takumi verifies.

It is currently published as a Developer Preview.

What it solves

AI agents can generate code, but the delivery trail, evidence, reviewability, and resumability are often fragile. takumi treats workflows and evidence as platform concerns so agent output can become deliverable software change.

Problem Takumi approach
AI tools generate code but lose the delivery trail Traceability matrix across requirements, design, tests, evidence, and review
Products lock users into one model or harness Runtime adapter API for fake, Pi, DeepSeek, CLI bridge, and future runtimes
Tests and evidence are treated as afterthoughts Evidence-native pipeline for unit and integration test deliverables
Agents can claim “done” too early Quality gates, held-out verifier tests, and independent verification
Long tasks lose state across context windows Manage-Execute-Audit loop with persistent task state
Domain delivery processes are hard to encode Japanese SI workflow as a first-party example

Quick Start

Install from source. npm package publishing is on the roadmap.

git clone https://github.com/sscodeai/takumi.git
cd takumi

pnpm install
pnpm build

Run a deterministic local task with no API key.

pnpm exec takumi init
pnpm exec takumi run "Implement user login API"

Run a workflow with a real runtime.

export COMMANDCODE_API_KEY=...
pnpm exec takumi run requirements.md --workflow jp-si-standard --runtime deepseek

Run the Manage-Execute-Audit loop.

pnpm exec takumi loop "Fix the sumEven bug and add tests" --runtime deepseek --max-rounds 5

Architecture

                          Takumi
                            |
                    Orchestration Core
                            |
        +-------------------+-------------------+
        |                   |                   |
      Skills              Tools             Workflows
        |                   |                   |
        +-------------------+-------------------+
                            |
                       Runtime API
                            |
          +-----------------+-----------------+
          |                 |                 |
         Pi              DeepSeek           CLI
          |                                   |
   More runtimes                       Any harness
takumi/
├── apps/cli/              # takumi CLI: init, run, loop, runtime list, extension list
├── apps/console/          # lightweight web console with SSE live logs
├── packages/core/         # workflow engine, runtime API, artifacts, traceability, MEA loop, sandbox
├── runtimes/              # fake, pi, deepseek, cli adapters
├── extensions/            # skills, tools, workflows
├── eval/                  # agent reliability evaluation tasks
├── bench/                 # system benchmark baselines
├── examples/              # end-to-end delivery examples, including Japanese SI
└── docs/                  # ADRs and evaluation notes

Core Ideas

  • Small Core: orchestration, task/event/artifact models, runtime abstraction, extension loading, approval, and audit.
  • Four extension kinds: Skill, Tool Plugin, Workflow Plugin, Runtime Adapter.
  • Harness agnostic: runTask, cancel, getStatus, getUsage, getArtifacts over a unified event stream.
  • Traceability by default: connects artifacts with IDs such as REQ-001 -> DESIGN-001 -> UT-001 -> EVIDENCE-001.
  • Human in the loop: workflows can declare approval gates.
  • Independent verification: agent claims are not trusted as completion evidence.

Features

Capability Status
Pluggable runtimes: fake / Pi / DeepSeek / CLI bridge Done
Declarative workflows, including Japanese SI / V-model Done
Skills for requirements, basic design, detailed design, tests, evidence, review Done
Traceability matrix generation Done
Approval gates Done
Durable resume from audit records Done
Parallel workflow step execution Done
Sandbox abstraction with unshare support Done
Web console with live logs Done
Agent Eval with held-out verifier tests and repair loop Done
MEA loop: Manage, Execute, Audit Done

Agent Eval

takumi ships an Agent Eval framework under eval/. It covers easy, hard, trap, no-self-test, complex, and implicit-constraint task groups. Each task has machine-verifiable verifier tests that are excluded from the agent prompt context.

TAKUMI_EVAL_HARNESS=deepseek TAKUMI_EVAL_MODEL=deepseek/deepseek-v4-flash node eval/scripts/run-eval.mjs
TAKUMI_EVAL_HARNESS=deepseek TAKUMI_EVAL_MODEL=deepseek/deepseek-v4-pro node eval/scripts/run-eval.mjs --tasks=ts-complex
TAKUMI_EVAL_HARNESS=pi node eval/scripts/run-eval.mjs
Model First-pass False completion Repair triggered
deepseek v4-flash 23/23 0% 0
deepseek v4-pro, complex 4/5 0% 1 natural repair
Pi, opencode-zen 6/6 0% 0

MEA Loop

The Manage-Execute-Audit loop breaks down long-horizon agent work and requires independent verification before completion.

  1. Manager owns persistent task state and decides the next subtask.
  2. Executor works in a fresh context and may modify the environment.
  3. Auditor independently verifies the resulting state.
  4. Only clean audit evidence can mark a task record complete.

Roadmap

  • Core types, runtime abstraction, and extension discovery
  • Workflow engine with DAG, approval gates, retry, and capability validation
  • Fake, Pi, DeepSeek, and CLI runtime adapters
  • Japanese SI skills and V-model workflow
  • Agent Eval and system benchmarks
  • Durable resume, parallel execution, web console, sandbox, and MEA loop
  • Claude runtime adapter
  • Excel, Word, Jira, GitHub, and Playwright tool plugins
  • npm package publishing
  • Real-repo-scale evals

Next

  • Read the README and examples in the repository
  • Browse other SSCodeAI projects in Projects
Navigation

Type to search…

↑↓ navigate↵ selectEsc close